GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction

Jianheng Liu, Yunfei Wan, Bowen Wang, Chunran Zheng, Jiarong Lin and Fu Zhang,

The University of Hong Kong,

Abstract

A unified LiDAR-visual system that synergizes Gaussian splatting with a neural signed distance field.

We propose a unified LiDAR-visual system that synergizes Gaussian splatting with a neural signed distance field. The accurate LiDAR point clouds enable a trained neural signed distance field to offer a manifold geometry field, This motivates us to offer an SDF-based Gaussian initialization for physically grounded primitive placement and a comprehensive geometric regularization for geometrically consistent rendering and reconstruction.

Shape Regularization

Illustration of different geometric regularization. The blue splats represent the initial splat, and the orange splats represent the optimized splat. The dashed lines represent the optimization directions.

Video

Experiments

Replica

We emphasize the issues of extrapolation rendering consistency by uniformly sampling positions and orientations in each scene to generate the extrapolation dataset from Replica.

InstantNGP

H2Mapping

3DGS

MonoGS

2DGS

PGSR

Ours

M2Mapping

FAST-LIVO2

InstantNGP

3DGS

2DGS

PGSR

RR+CR

M2Mapping

Ours(RR+SR)

* RR: Render Regularization, CR: Center Regularization, SR: Structure Regularization.

Surface Reconstruction Results

Compressed Mesh.

FAST-LIVO2

Campus

Sculpture

Culture

Drive

Station

CBD

SYSU

BibTeX


          @misc{liu2025gssdflidaraugmentedgaussiansplatting,
            title={GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction}, 
            author={Jianheng Liu and Yunfei Wan and Bowen Wang and Chunran Zheng and Jiarong Lin and Fu Zhang},
            year={2025},
            eprint={2503.10170},
            archivePrefix={arXiv},
            primaryClass={cs.RO},
            url={https://arxiv.org/abs/2503.10170}, 
          }